← Back to community benchmarks

gemma-4-12B-it

M4 Max (40c) · 64 GB · 8bit · 2026-06-04

Performance

32k

tokens

452.1

PP tok/s

28.5

TG tok/s

72483

TTFT (ms)

15.1

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.4.2.dev2

macOS macOS 26.5.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
16k	487.3	30.1	13.9 GB	view
32k	452.1	28.5	15.1 GB	current
64k	379.4	23.7	17.1 GB	view